Articles
Daily digests summarizing the vulnerabilities and incidents tracked by VulnWatch.
-
· 2 entries · daily · Subscribers only
Axolotl RCE and Rowboat SSRF: Critical Risks in AI Tooling
New vulnerabilities in Axolotl and Rowboat expose AI pipelines to remote code execution and server-side request forgery, demanding immediate patching and configuration audits for ML platforms.
-
· 45 entries · daily · Subscribers only
VulnWatch Digest: Critical RCE in AI Agents and Widespread SSRF in Model Serving
Today's digest highlights critical remote code execution flaws in CodeWhale and LaVague agents, alongside a wave of SSRF vulnerabilities in OpenAI-compatible APIs. Immediate patching is required for multiple high-severity issues affecting Langflow, vLLM, and Hugging Face tokenizers.
-
· 18 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE in Claude Code, SSRF in Unstructured, and Auth Bypasses
Today's digest highlights critical remote code execution in Claude Code Studio, full-read SSRF in the ubiquitous Unstructured library, and severe authentication bypasses in MISP and Copilot Studio affecting AI supply chains.
-
· 13 entries · daily · Subscribers only
VulnWatch Daily: Critical Agentic RCE and LiteLLM Auth Bypasses
Today's digest highlights critical vulnerabilities in agentic frameworks allowing shared bundle overwrites and RCE, alongside active exploitation of LiteLLM authentication flaws and supply-chain risks in model training data handlers.
-
· 7 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE in Elasticsearch ML and Supply Chain Risks
Today's digest highlights a critical deserialization flaw in Elasticsearch ML enabling RCE, a recursion DoS in llama.cpp, and supply chain vulnerabilities in Scrapy and pnpm affecting AI data pipelines.
-
· 13 entries · daily · Subscribers only
MCPHub Critical Flaws and Agentic RCE Risks Dominate August 31 Vulnerability Landscape
A surge of critical vulnerabilities in MCPHub and Eclipse Theia exposes agentic systems to RCE, SSRF, and prompt injection attacks, demanding immediate patching and architectural review.
-
· 93 entries · weekly
VulnWatch Weekly: The MCP Security Crisis & Langflow RCE
This week marks a turning point for AI security with critical RCEs in Langflow and a systemic collapse of authentication in the Model Context Protocol (MCP) ecosystem. Immediate patching is required for Kubeflow, Langflow, and all exposed MCP servers.
-
· 5 entries · daily · Subscribers only
VulnWatch Digest: API Key Leaks, DOMPurify Bypasses, and Cleartext Secrets
Today's digest highlights critical credential exposure in NextChat and browser-use, a DOMPurify bypass in Readest enabling RCE, and data leakage flaws in Ash framework libraries affecting ML audit trails.
-
· 24 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE in Langflow, Kubeflow SSRF, and Agent Supply Chain Risks
Today's digest highlights a catastrophic command execution chain in IBM Langflow, a CVSS 10.0 SSRF in Kubeflow Pipelines, and emerging risks in AI agent orchestration and LLM proxy authentication bypasses.
-
· 9 entries · daily · Subscribers only
Critical MCP Server Exposure and Supply Chain Risks in AI Agents
A wave of critical vulnerabilities exposes Model Context Protocol (MCP) servers to unauthenticated access and credential theft, while supply chain flaws threaten mobile AI integrations and data integrity.
-
· 4 entries · daily · Subscribers only
VulnWatch Daily: RCE in whichllm, GitLab CI Agent Flaws, and Fleet Data Leaks
Today's digest covers critical code injection in whichllm via HuggingFace filenames, command execution in GitLab's Claude agent, and sort-order oracle vulnerabilities in Fleet exposing enrollment secrets.
-
· 46 entries · daily · Subscribers only
VulnWatch Daily: Critical RCE and Auth Bypasses in MCP Ecosystem
August 25, 2026: A surge of critical vulnerabilities targets the Model Context Protocol (MCP) ecosystem, featuring unauthenticated RCE via command injection, unsafe math parsing, and widespread authentication bypasses in agentic frameworks.
-
· 4 entries · daily · Subscribers only
VulnWatch Daily: RCE in Xinference, CLI Shell Escapes, and SSRF Gaps
Today's digest covers critical RCE risks in Xinference's model loading, shell command bypasses in Continue CLI, incomplete SSRF fixes in BentoML, and a DoS vector in llama.cpp RPC servers.
-
· 98 entries · weekly
VulnWatch Weekly: The Week of Unsafe Eval, Agent RCE, and Active SSRF
This week's digest highlights a critical wave of Remote Code Execution (RCE) vulnerabilities in LLM inference servers, driven by unsafe deserialization and dynamic code evaluation. Most urgently, CISA has added an actively exploited MLflow SSRF flaw to its KEV catalog, demanding immediate patching for all exposed instances.
-
· 1 entry · daily · Subscribers only
VulnWatch Digest: Critical Deserialization Flaw in llama.cpp RPC
A new medium-severity RCE vulnerability (CVE-2026-78147) targets the ggml-RPC server in llama.cpp, exploiting unsafe deserialization of tensor parameters. Immediate patching is required for distributed inference deployments.